Two teenage founders walked into Y Combinator co-founder Paul Graham’s backyard with an idea that no one in agriculture seemed to want: an AI model that could help design better pesticides. By the time they left, they had a new business model and a new company, eventually gaining support from Graham.
Now, that reimagined company, Bindwell, has raised $6 million in a seed round co-led by General Catalyst and A Capital, with a personal check from Graham himself. Rather than selling AI tools to traditional agrochemical giants, the startup designs new pesticide molecules in-house using its own models and licenses the IP directly. This is a shift in strategy aimed at modernizing a legacy industry still dominated by decades-old chemistry.
According to the Food and Agriculture Organization of the United Nations, the use of pesticides in agriculture has doubled in the past 30 years, but up to 40% of global crop production is still lost to pests and diseases each year. As pests evolve and develop resistance, farmers are forced to use more chemicals just to maintain the same yield, a cycle that damages ecosystems and further accelerates resistance. Although regulatory pressures are increasing, most agrochemical companies still rely on tweaking traditional compounds. Bindwell is betting that AI can break this cycle by discovering entirely new, more targeted molecules – molecules designed from the ground up to meet modern challenges.
Founded in 2024 by Tyler Rhodes, 18, and Naveer Anand, 19, Bindwell applies AI-driven drug discovery technology to agriculture with the goal of speeding the identification and testing of new pesticide molecules.
Bindwell began as a research project in late 2023 when Rose and Anand were students in the Wolfram Summer Research Program. They initially focused on a drug discovery AI model called PLAPT that includes binding affinity prediction. The study was later cited in a Nature Scientific Reports paper on cancer treatments. In 2024, they began looking at how the same approach could be applied to pesticides.
Both founders were personally exposed to this issue. Rose learned about the challenges of pest control from her aunt, who is a farmer in China. Anand’s family owns farmland in Delhi, where he saw firsthand the impact of limited pesticide options on crop yields.
“Agriculture was in our hearts,” Rose said in an interview. “That led to the realization that we can use exactly the same techniques that have been successful in drug discovery. The biochemistry is the same, so we can bring that to pesticide discovery. But pesticides are a huge problem that I feel like most people don’t pay much attention to.”
tech crunch event
san francisco
|
October 13-15, 2026
Rose and Anand joined Y Combinator’s Winter 2025 batch with plans to build AI models and sell access to them to large agrochemical companies. However, they failed to find traction. Most industry players have been reluctant to embrace AI as a core part of pesticide discovery. Halfway through the program, they were invited to Paul Graham’s house and spoke with him for about 45 minutes in his backyard.
After hearing about their challenges, Graham suggested a different approach. Rather than selling tools, we use our own models to discover new pesticide molecules ourselves. This conversation was the beginning of Bindwell’s current direction.
“The founders[of Bindwell]are probably fine. They’re smart and have good ideas,” he later wrote on X.
Bindwell has developed a proprietary AI suite designed to reduce hallucinations, a common problem where models produce unreliable or unsupported output. This software includes Foldwell, a structural prediction model. This is a finely tuned version of DeepMind’s AlphaFold, which is used to identify the structure of target proteins. Also included is PLAPT, an open-source protein-ligand interaction model that can scan all known synthetic compounds in under 6 hours, and APPT, a protein-protein interaction model for biopesticide screening that outperforms existing tools by 1.7x on affinity benchmark v5.5. Additionally, the suite includes an uncertainty quantification system that flags when results are reliable and when more data is needed.
“We’re not selling AI models, so we don’t compete with companies that sell models,” Rose told TechCrunch.
Combined, Bindwell’s models can analyze “billions” of molecules and deliver four times faster performance than DeepMind’s AlphaFold 3, the company says.
“Currently, the way most pesticides are discovered is not goal-based,” Rose says. “Entomologists and chemists propose different compounds and test them on insects. Often thousands of chemicals need to be synthesized and tested, making it expensive just to confirm their effectiveness. Using our AI model, we can simplify the problem down to a single protein.”
This AI can help identify proteins that are unique to certain pests but not present in humans, beneficial insects, or aquatic organisms such as daphnia.
“Once we find those proteins, we can design something that binds to them and stops them from working,” Rose says.
Bindwell is currently testing the effectiveness of AI-generated molecules at its San Carlos laboratory. Rose also is working with third-party partners to further validate the model, although he declined to provide further details.
Rose said the startup is in early discussions with several global agrochemical companies and expects to close its first partnership agreement soon. “After a year, we hope to enter into licensing agreements with some of these companies,” he said. Bindwell has also begun discussions with stakeholders in India and China to conduct field trials.
The startup currently has a team of four people and also works with external contractors on molecular synthesis.
Along with Graham, SV Angel also participated in Bindwell’s seed round. Before joining Y Combinator’s Winter 2025 batch, the startup raised a pre-seed round of funding from Character Capital.
